检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Xuesong Li Yating Liu Kunfeng Wang Yong Yan Fei-Yue Wang The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China College of Information Science and Technology Beijing University of Chemical Technology Beijing China State Grid Zhejiang Electric Power Company LTD Hangzhou China

Existing pedestrian re-identification methods based on deep learning have achieved good results under constrained conditions. However, there exist some challenges including large human pose variations, viewpoint changes, severe occlusions and imprecise detection of persons. So we present a Hard/Soft hybrid Attention Network (HSAN) that combines pose information and attention mechanism to deal with the challenges. Our model includes two main parts: Pose-guided Hard Attention (PHA) and Regional Soft Attention (RSA). PHA uses the keypoints generated by pose estimation to enhance the foreground information, and RSA is learned to eliminate the background clutter. We extract reliable features and locate discriminative regions by using these two modules to handle occlusions, pose changes and background noises. We conduct a lot of experiments on public datasets including DukeMTMC-ReID, Market-1501, and CUHK03, and the results show that our method achieves stateof-the-art performance.

关键词： Pose estimation Task analysis Noise measurement Feature extraction Reliability Machine learning

来源：评论

学校读者我要写书评

暂无评论

Broad learning system based on maximum correntropy criterion

arXiv

引用

arXiv 2019年

作者： Zheng, Yunfei Chen, Badong Wang, Shiyuan Wang, Weiqun Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an710049 China College of Electronic and Information Engineering Southwest University Chongqing400715 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

As an effective and efficient discriminative learning method, Broad Learning System (BLS) has received increasing attention due to its outstanding performance in various regression and classification problems. However, the standard BLS is derived under the minimum mean square error (MMSE) criterion, which is, of course, not always a good choice due to its sensitivity to outliers. To enhance the robustness of BLS, we propose in this work to adopt the maximum correntropy criterion (MCC) to train the output weights, obtaining a correntropy based broad learning system (C-BLS). Thanks to the inherent superiorities of MCC, the proposed C-BLS is expected to achieve excellent robustness to outliers while maintaining the original performance of the standard BLS in Gaussian or noise-free environment. In addition, three alternative incremental learning algorithms, derived from a weighted regularized least-squares solution rather than pseudoinverse formula, for C-BLS are developed. With the incremental learning algorithms, the system can be updated quickly without the entire retraining process from the beginning, when some new samples arrive or the network deems to be expanded. Experiments on various regression and classification datasets are reported to demonstrate the desirable performance of the new methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Fault Tolerant control for a Class of Nonlinear System based on Active Disturbance Rejection control and RBF Neural Networks 36

Fault Tolerant Control for a Class of Nonlinear System based...

引用

第36届中国控制会议

作者： Lushan Zhou Liling Ma Junzheng Wang State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology

ISBN: (纸本)9781538629185

In this paper,a fault tolerant control method based on active disturbance rejection control(ADRC) and radial basis function neural network(RBFNN) is proposed for a class of multi-input-multi-output nonlinear system with actuator faults,components faults and sensor *** proposed method does not rely on the plant *** regarding the faults and plant uncertainties as the disturbance,through the observation of extended state observer and the compensation of feedback control signal,this method achieves the fault tolerance control of the plant with component fault and actuator *** sensor faults,in this work,radial basis function neural network is applied to estimate the real output of the *** this output estimation is utilized by active disturbance rejection control to achieve the fault tolerance of ***,the effectiveness of the proposed method is validated by the simulation results of the three-tank system.

关键词： Fault tolerant control active disturbance rejection control radial basis function neural network

来源：评论

学校读者我要写书评

暂无评论

Hazard-evaluation-oriented Moving Horizon Parallel Steering control for Driver-Automation Collaboration During Automated Driving

引用

IEEE/CAA Journal of Automatica Sinica 2018年第6期5卷 1062-1073页

作者： Hongyan Guo Linhuan Song Jun Liu Fei-Yue Wang Dongpu Cao Hong Chen Chen Lv Partick Chi-Kwong Luk State Key Laboratory of Automotive Simulation and Control and the Department of Con-trol Science and Engineering Jilin University(Campus Nanling)Changchun130025China State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense TechnologyChangsha 410073China Mechanical and Mechatronics Engineering Department at the University ot Waterloo 200 University Avenue West WaterlooONNZL3G1Canada Department of Automotive Engineering Cranfield UniversityBedfordshire MK43 0ALUK School of Water Energy and EnvironmentCranfield UniversityBedfordshire MK43 0ALUK

Prompted by emerging developments in connected and automated vehicles, parallel steering control, one aspect of parallel driving, has become highly important for intelligent vehicles for easing the burden and ensuring the safety of human drivers. This paper presents a parallel steering control framework for an intelligent vehicle using moving horizon *** framework considers lateral stability, collision avoidance and actuator saturation and describes them as constraints, which can blend the operation of a human driver and a parallel steering controller effectively. Moreover, the road hazard and the steering operation error are employed to evaluate the operational hazardous of an intelligent vehicle. Under the hazard evaluation,the intelligent vehicle will be mainly operated by the human driver when the vehicle operates in a safe and stable *** automated steering driving objective will play an active role and regulate the steering operations of the intelligent vehicle based on the hazard evaluation. To verify the effectiveness of the proposed hazard-evaluation-oriented moving horizon parallel steering control approach, various validations are conducted, and the results are compared with a parallel steering scheme that does not consider automated driving situations. The results illustrate that the proposed parallel steering controller achieves acceptable performance under both conventional conditions and hazardous conditions.

关键词： Hazard evaluation intelligent vehicle atera stability moving horizon optimization paralle steering control

来源：评论

学校读者我要写书评

暂无评论

Parallel Dispatch:A New Paradigm of Electrical Power System Dispatch

引用

IEEE/CAA Journal of Automatica Sinica 2018年第1期5卷 311-319页

作者： Jun Jason Zhang Fei-Yue Wang Qiang Wang Dazhi Hao Xiaojing Yang David Wenzhong Gao Xiangyang Zhao Yingchen Zhang Department of Electrical and Computer Engineering Ritchie School of Engineering and Computer Science University of Denver Denver 80210 CO USA State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Science (SKL-MCCS CASIA) Beijing 100190 China Research Center of Computational Experiments and Parallel Systems The National University of Defense Technology Changsha 410073 China State Grid Tianjin Electric Power Company Tianjin 300010 China School of Automation Science and Electrical Engineering Beihang University Beijing 100191 China National Renewable Energy Laboratory Golden CO 80401 USA IEEE

Modern power systems are evolving into sociotechnical systems with massive complexity, whose real-time operation and dispatch go beyond human capability. Thus,the need for developing and applying new intelligent power system dispatch tools are of great practical significance. In this paper, we introduce the overall business model of power system dispatch, the top level design approach of an intelligent dispatch system, and the parallel intelligent technology with its dispatch applications. We expect that a new dispatch paradigm,namely the parallel dispatch, can be established by incorporating various intelligent technologies, especially the parallel intelligent technology, to enable secure operation of complex power grids,extend system operators' capabilities, suggest optimal dispatch strategies, and to provide decision-making recommendations according to power system operational goals.

关键词： ACP knowledge automation power dispatch parallel dynamic programming parallel intelligence paralle learning situational awareness

来源：评论

学校读者我要写书评

暂无评论

A Novel Forwarding Method for Full-Duplex Two-Way Relay Networks

引用

China Communications 2017年第4期14卷 65-72页

作者： Shuangshuang Han Xiang Cheng Liuqing Yang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of SciencesBeijing China and Qingdao Academy of Intelligent Industries The State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Engineering and Computer Science Peking University Department of Electrical and Computer Engineering Colorado State University

An estimate-and-forward(EF) scheme for single-input single-output(SISO) and multiple-input multiple-output(MIMO) full-duplex two-way relay networks is proposed and analyzed. The relay estimates the received signal from two terminal nodes by a minimum mean squared error(MMSE) estimation and forwards a scaled version of the MMSE estimate to the destination. The proposed EF outperforms conventional amplify-and-forward(AF) and decode-and-forward(DF) across all signal-to-noise ratio(SNR) region. Because its computational complexity is high for relays with a large number of antennas(large MIMO) and/or high order constellations, an approximate EF scheme, called list EF, are thus proposed to reduce the computational complexity. The proposed list EF computes a candidate list for the MMSE estimate by using a sphere decoder, and it approaches the performance of the exact EF relay at a negligible performance loss. The proposed forwarding approach also could be used to other relay networks, such as half-duplex, one-way or massive MIMO relay networks.

关键词： estimate-and-forward full-duplex two-way relay wireless communications

来源：评论

学校读者我要写书评

暂无评论

Raunet: Residual attention u-net for semantic segmentation of cataract surgical instruments

arXiv

引用

arXiv 2019年

作者： Ni, Zhen-Liang Bian, Gui-Bin Zhou, Xiao-Hu Hou, Zeng-Guang Xie, Xiao-Liang Wang, Chen Zhou, Yan-Jie Li, Rui-Qi Li, Zhen University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Cas Center for Excellence in Brain Science and Intelligence Technology Beijing100190 China

Semantic segmentation of surgical instruments plays a cru-cial role in robot-assisted surgery. However, accurate segmentation of cataract surgical instruments is still a challenge due to specular reec-tion and class imbalance issues. In this paper, an attention-guided net-work is proposed to segment the cataract surgical instrument. A new at-tention module is designed to learn discriminative features and address the specular reection issue. It captures global context and encodes se-mantic dependencies to emphasize key semantic features, boosting the feature representation. This attention module has very few parameters, which helps to save memory. Thus, it can be exibly plugged into other networks. Besides, a hybrid loss is introduced to train our network for addressing the class imbalance issue, which merges cross entropy and logarithms of Dice loss. A new dataset named Cata7 is constructed to evaluate our network. To the best of our knowledge, this is the first cataract surgical instrument dataset for semantic segmentation. Based on this dataset, RAUNet achieves state-of-the-art performance 97.71% mean Dice and 95.62% mean IOU. Copyright © 2019, The Authors. All rights reserved.

关键词： Surgical equipment

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Features Comparison Between Back-Propagation and Extreme Learning Machine

Convolutional Neural Network Features Comparison Between Bac...

引用

第37届中国控制会议

作者： Atmane Khellal Hongbin Ma Qing Fei School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology

Recently deep learning based architectures have been widely deployed in many problems of artificial *** deep learning models, Convolutional Neural Networks（CNN） have been reported in numerous successful applications such as object recognition, and natural language processing. The convolutional neural networks are trained by back-propagating the classification error using the Back-Propagation（BP） algorithm, which requires a large amount of data and slows the training process. To overcome these difficulties, a new fast and accurate approach based on Extreme Learning Machine（ELM） to train any convolutional neural network has been proposed. The developed framework（ELM-CNN） is based on the concept of autoencoding to learn the convolutional filters with biases, by reconstructing the normalized input and the intercept term. In this paper, systematic comparison with traditional back-propagation based training method（BP-CNN） has been made with respect to two aspects qualitative and quantitative. The experimental results on the popular MNIST dataset show that the ELM-CNN algorithm achieves competitive results in terms of generalization performance and up to 16 times faster than the back-propagation based training of CNN.

关键词： Convolutional Neural Network Extreme Learning Machine Features Comparison Visualization

来源：评论

学校读者我要写书评

暂无评论

Relaying Strategy Based on Estimated Information for Multi-Antenna Cooperative Networks

引用

China Communications 2017年第8期14卷 157-165页

作者： Shuangshuang Han Peng Zhang Feijin Shi Fei-Yue Wang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of SciencesBeijingChina and Qingdao Academy of Intelligent Industries School of Computer Engineering Weifang University Communications Headquarters Ministry of Foreign Affairs of the People's Republic of China State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijingChina and Research Center of Computational Experiments and Parallel SystemsThe National University of Defense Technology

A sphere-based list forwarding scheme for multiple-input multiple-output(MIMO) relay networks is proposed and analyzed. Firstly, an estimate forwarding(EF) method is proposed, which forwards the minimum mean squared error(MMSE) estimate of the source data to the destination. Since it performs like amplify-and-forward(AF) and decode-and-forward(DF) for the low and high signal-to-noise ratio(SNR) regions, respectively, the EF relay thus outperforms conventional AF and DF across all SNRs without the need for switching algorithms for different SNRs. Because computational complexity is however high for relays with a large number of antennas(large MIMO) and/or high order constellations, list EF for large MIMO relay networks is proposed. It computes a list sphere decoder based MMSE estimate and retains the advantages of the exact EF relay at a negligible performance loss. The proposed list EF could offer a flexible trade-off between the performance and computational complexity.

关键词： MIMO system cooperative network soft information

来源：评论

学校读者我要写书评

暂无评论

A General 6-DOF Industrial Robot Arm control System Based on Linux and FPGA

A General 6-DOF Industrial Robot Arm Control System Based on...

引用

第30届中国控制与决策会议

作者： Cong Han Hongbin Ma Wenchao Zuo Sunjie Chen Xinghong Zhang School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology

This paper presents a general six degrees of freedom(6-DOF) robot arm control system based on Linux and field-programmable gate array(FPGA).The system provides a friendly human-computer interaction *** can complete palletizing,handling and other processes through simple programming of the interactive *** adopt industrial personal computer(IPC) as the controller to accomplish the kinematics calculation,design motion control board connected with the controller and the servo system,and use the servo system to implement the motion of the robot *** kinematics calculation and trajectory generation based on cubic polynomial are developed based on the Linux system,which improves the portability of the *** a normal method is adopted in updating trajectory points to improve *** control board is designed based on FPGA,which with the characteristic of parallel computing raises the running speed of the robot arm.

关键词： 6-DOF industrial robot arm control system human-machine interaction Linux FPGA

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：